Update app.py

app.py

@@ -1,6 +1,69 @@
 import subprocess
-subprocess.run(["pip", "install","gradio"])
+subprocess.run(["pip", "install","gradio","transformers"])
 import gradio as gr
+import transformers
+
+# Define a function for generating text based on a prompt using the fine-tuned GPT-2 model and the tokenizer
+def generate_text(prompt, length=100, theme=None, **kwargs):
+
+    model_url = "https://huggingface.co/spaces/sailormars18/Yelp-reviews-usingGPT2/blob/main/pytorch_model.bin"
+    
+    # Load the model from the Hugging Face space
+    model = transformers.GPT2LMHeadModel.from_pretrained(model_url).to(device)
+    
+    # Load the tokenizer from the Hugging Face space
+    tokenizer = transformers.GPT2Tokenizer.from_pretrained(model_url)
+
+    # If a theme is specified, add it to the prompt as a prefix for a special token
+    if theme:
+        prompt = ' <{}> '.format(theme.strip()) + prompt.strip()
+
+    input_ids = tokenizer.encode(prompt, return_tensors='pt').to(device)
+    attention_mask = torch.ones(input_ids.shape, dtype=torch.long, device=device)
+    pad_token_id = tokenizer.eos_token_id
+
+    # Set the max length of the generated text based on the input parameter
+    max_length = length if length > 0 else 100
+
+    sample_outputs = model.generate(
+        input_ids,
+        attention_mask=attention_mask,
+        pad_token_id=pad_token_id,
+        do_sample=True,
+        max_length=max_length,
+        top_k=50,
+        top_p=0.95,
+        temperature=0.8,
+        num_return_sequences=1,
+        no_repeat_ngram_size=2,
+        repetition_penalty=1.5,
+    )
+    generated_text = tokenizer.decode(sample_outputs[0], skip_special_tokens=True)
+
+    # Post preprocessing of the generated text
+    
+    # Remove any leading and trailing quotation marks
+    generated_text = generated_text.strip('"')
+
+    # Remove leading and trailing whitespace
+    generated_text = generated_text.strip()
+
+    # Find the special token in the generated text and remove it
+    match = re.search(r'<([^>]+)>', generated_text)
+    if match:
+        generated_text = generated_text[:match.start()] + generated_text[match.end():]
+
+    # Remove any leading numeric characters and quotation marks
+    generated_text = re.sub(r'^\d+', '', generated_text)
+    generated_text = re.sub(r'^"', '', generated_text)
+
+    # Remove any newline characters from the generated text
+    generated_text = generated_text.replace('\n', '')
+
+    # Remove any other unwanted special characters
+    generated_text = re.sub(r'[^\w\s]+', '', generated_text)
+    
+    return generated_text.strip().capitalize()
 
 # Define a Gradio interface for the generate_text function, allowing users to input a prompt and generate text based on it
 iface = gr.Interface(